AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Bootstrapped Representations in Reinforcement Learning

Charline Le Lan, Stephen Tu, Mark Rowland, Anna Harutyunyan, Rishabh Agarwal, Marc G Bellemare, Will Dabney

ICML 2023 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Pretrain DQN representations with auxiliary cumulant-value predictionsDQN · Four Roomsonline performanceImproved
Pretrain DQN representations with auxiliary cumulant-value predictionsDQN · Sparse Mountain Caronline performanceImproved
Use ExactSVD or CCR cumulants for offline pretrainingDQN · Four Rooms and Sparse Mountain Caronline performanceImproved
Use indicator cumulants instead of isotropic random cumulants (ablation)supervised auxiliary training · Four Roomssubspace recovery errorHurt
Use orthogonal cumulant columns (ablation)supervised auxiliary training · Four Roomssubspace recovery errorImproved
Use standard Gaussian rather than unit-norm Gaussian cumulants (ablation)TD auxiliary training · Four Roomssubspace recovery errorHurt
Normalize Gaussian cumulant columns to unit norm (ablation)TD auxiliary training · Four Roomssubspace recovery errorImproved
Use indicator cumulants rather than Gaussian cumulants (ablation)TD auxiliary training · Four Roomssubspace recovery errorImproved
Use orthogonal cumulant columns (ablation)TD auxiliary training · Four Roomssubspace recovery errorImproved
Use isotropic rather than non-isotropic cumulant distributions (ablation)TD auxiliary training · Four Roomssubspace recovery errorNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy